© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66530
    Prev
    Next
    INDEX
    Explanations

    May you share freely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    וּ
    -1.47
     mengangg
    -1.34
     اهم
    -1.27
     ferdig
    -1.25
    Firstly
    -1.23
     magasiner
    -1.23
    ೭
    -1.22
    Leírás
    -1.17
     تغي
    -1.17
     ataupun
    -1.17
    POSITIVE LOGITS
     “
    1.23
     self
    1.23
     energy
    1.22
     ‘
    1.18
     ability
    1.17
     Angebote
    1.16
     [
    1.16
     family
    1.14
     I
    1.13
     T
    1.09
    Activations Density 0.022%

    No Known Activations